Ke Bao 9fafa62db7 Share target model embed and head weights for nextn (#4033)

2025-03-03 13:30:04 -08:00

..

cuda_graph_runner.py

Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)

2025-03-03 00:12:04 -08:00

forward_batch_info.py

Share target model embed and head weights for nextn (#4033)

2025-03-03 13:30:04 -08:00

model_runner.py

Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)

2025-03-03 00:12:04 -08:00